Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Smoking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     southern
    -0.07
     breakers
    -0.07
    огод
    -0.07
     Georg
    -0.07
    filesystem
    -0.07
     повед
    -0.07
     Gel
    -0.07
     popularity
    -0.07
     Routes
    -0.07
    ogenen
    -0.07
    POSITIVE LOGITS
     worsen
    0.09
    —even
    0.09
     exacerb
    0.09
    uffy
    0.09
     erection
    0.09
     wors
    0.09
     cannabis
    0.09
    —which
    0.08
    orst
    0.08
     tobacco
    0.08
    Act Density 0.004%

    No Known Activations